Character image generation method and device, terminal equipment and storage medium

Abstract

The invention discloses a character generation method and device, terminal equipment and a storage medium, and belongs to the technical field of terminals. The method comprises the steps of obtaining a model parameter file, wherein the model parameter file comprises model parameters for adjusting a first character model according to an image collected by a first user to generate a first character image; and sending the model parameter file to a second terminal device, so that the second terminal device adjusts the second character model according to model parameters contained in the model parameter file to generate a second character image. When a self-generated first character image is shared, a first terminal device adjusts a first character model according to an image collected by a first user to generate a model parameter of the first character image, the model parameter file is packaged into a model parameter file, and the model parameter file is sent to a second terminal device; and the second terminal device generates the second character image according to the model parameters in the model parameter file, so that the efficiency of generating the character image is improved.

Description

Technical Field

[0001] The present application relates to the field of terminal technology, and in particular to a method, apparatus, terminal device and storage medium for generating a character image. Background Art

[0002] With the development of science and technology, various terminal devices appear in people's daily lives. People can use terminal devices for entertainment, learning, etc., and can also use terminal devices for interaction and transmission of video and audio data.

[0003] Among them, when users use terminal devices to interact, some applications can also provide functions such as dynamic expressions, and users can generate dynamic expressions independently, share and send dynamic expressions, etc. At present, in terminal devices, when generating dynamic expressions with three-dimensional models, it is usually necessary to collect the user's facial image or body image, apply the user's facial image or body image to the three-dimensional model, and generate a character image that conforms to the user's facial image or body image. In this application, when the first user shares the dynamic expression generated by himself, he directly sends the generated dynamic expression to other users. If other users want to generate the same dynamic expression by themselves, they can only download all the data of the dynamic expression or use their own terminal devices to collect and generate the first user again. The generation process is cumbersome, the amount of data to be transmitted is large, and there is a problem of low efficiency in generating character images. Summary of the invention

[0004] In order to simplify the process of generating a character image and improve the efficiency of generating a character image, the embodiment of the present application provides a method, apparatus, terminal device and storage medium for generating a character image. The technical solution is as follows:

[0005] In one aspect, the present application provides a method for generating a character image, which is applied to a first terminal device, and the method includes:

[0006] Acquire a model parameter file, wherein the model parameter file includes model parameters for adjusting a first character model according to an image collected from a first user to generate a first character image;

[0007] The model parameter file is sent to a second terminal device, so that the second terminal device adjusts the second character model according to the model parameters included in the model parameter file to generate a second character image.

[0008] In one aspect, the present application provides a method for generating a character image, which is applied to a second terminal device, and the method includes:

[0009] Receiving a model parameter file, wherein the model parameter file includes model parameters for the first terminal device to adjust the first character model according to the image collected from the first user to generate the first character image;

[0010] According to the model parameters included in the model parameter file, the second character model is adjusted to generate a second character image.

[0011] In one aspect, the present application provides a device for generating a character image, applied to a first terminal device, the device comprising:

[0012] A first acquisition module, used to acquire a model parameter file, wherein the model parameter file includes model parameters for generating a first character image by adjusting a first character model according to an image collected from a first user;

[0013] The first sending module is used to send the model parameter file to the second terminal device, so that the second terminal device adjusts the second character model according to the model parameters included in the model parameter file to generate a second character image.

[0014] In one aspect, the present application provides a device for generating a character image, characterized in that it is applied to a second terminal device, and the device includes:

[0015] A first receiving module, configured to receive a model parameter file, wherein the model parameter file includes model parameters of a first character image generated by adjusting a first character model by a first terminal device according to an image collected from a first user;

[0016] The first generating module is used to adjust the second character model according to the model parameters included in the model parameter file to generate a second character image.

[0017] In another aspect, the present application provides a terminal device, which includes a processor and a memory, wherein the memory stores a computer program, and the computer program is executed by the processor to implement the method for generating a human image as described in one aspect.

[0018] In another aspect, the present application provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is executed by a processor to implement the method for generating a human image as described in one aspect.

[0019] On the other hand, an embodiment of the present application provides a computer program product. When the computer program product is run on a computer, the computer is enabled to execute the method for generating a human image as described in one aspect above.

[0020] On the other hand, an embodiment of the present application provides an application publishing platform, which is used to publish a computer program product, wherein when the computer program product runs on a computer, the computer executes the character image generation method described in one aspect above.

[0021] The beneficial effects brought by the technical solution provided by the embodiment of the present application include at least:

[0022] The present application obtains a model parameter file, wherein the model parameter file contains model parameters for adjusting a first character model according to an image collected from a first user to generate a first character image; the model parameter file is sent to a second terminal device, so that the second terminal device adjusts the second character model according to the model parameters contained in the model parameter file to generate a second character image. When sharing the first character image generated by itself, the model parameters for adjusting the first character model according to the image collected from the first user by the first terminal device are packaged into a model parameter file, and the model parameter file is sent to the second terminal device, so that the second terminal device generates the second character image according to the model parameters in the model parameter file. The first terminal device does not need to transmit all the data of the first character image, which reduces the amount of data that needs to be transmitted, so that the second terminal device can generate the second character image more quickly, thereby improving the efficiency of generating character images. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 is a schematic diagram of an interface of an application program involved in an exemplary embodiment of the present application;

[0025] Figure 2 is a schematic diagram of an example structure of a terminal device provided in an embodiment of the present application;

[0026] Figure 3 is a method flow chart of a method for generating a character image provided by an exemplary embodiment of the present application;

[0027] Figure 4 is a method flow chart of a method for generating a character image provided by an exemplary embodiment of the present application;

[0028] Figure 5 is a method flow chart of a method for generating a character image provided by an exemplary embodiment of the present application;

[0029] Figure 6 is a schematic diagram of a character selection interface involved in an exemplary embodiment of the present application;

[0030] Figure 7 is a schematic diagram of an interface of a file selection interface involved in an exemplary embodiment of the present application;

[0031] Figure 8 is a schematic diagram of another file selection interface involved in an exemplary embodiment of the present application;

[0032] Fig. 9 It is a schematic diagram of an interface of a file receiving interface involved in an exemplary embodiment of the present application;

[0033] Fig.10 It is a schematic diagram of an interface of a file editing interface involved in an exemplary embodiment of the present application;

[0034] Fig.11 is a schematic diagram of another character selection interface involved in an exemplary embodiment of the present application;

[0035] Fig.12 is a method flow chart of a method for generating a character image provided by an exemplary embodiment of the present application;

[0036] Fig.13 is a structural block diagram of a character image generation device provided by an exemplary embodiment of the present application;

[0037] Fig.14 is a structural block diagram of a character image generation device provided by an exemplary embodiment of the present application;

[0038] Fig.15 It is a structural diagram of another example of the character image generation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0040] The term "multiple" as used herein refers to two or more than two. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the related objects are in an "or" relationship.

[0041] The solution provided by the present application can be used in real-life scenarios in which people use terminal devices in their daily lives to generate and share some dynamic character images inside terminal devices. To facilitate understanding, the application scenarios involved in the embodiments of the present application are briefly introduced below.

[0042] With the development of science and technology, various terminal devices have appeared in people's daily lives. People can use terminal devices for entertainment, learning, etc., and the terminal devices provide more and more functions, such as sending messages, sharing images, sharing emoticons, etc.

[0043] Please refer to Figure 1 , which shows a schematic diagram of an interface of an application program involved in an exemplary embodiment of the present application. Figure 1 As shown, the application interface 100 includes various character models 101, and the user can select one of the character models and process it so that the terminal device can generate the character image he wants.

[0044] In a terminal device, when generating dynamic expressions such as a three-dimensional model, it is usually necessary to collect the user's facial image or body image, apply the user's facial image or body image to the three-dimensional model, and generate a character image that matches the user's facial image or body image. Figure 1 In the interface shown, after the user selects the first character model, he or she records his or her own facial image through the camera, allowing the terminal device to collect his or her own facial image. The terminal device then applies the facial image to the character model selected by the user to generate a character image with the same expression as his or her own.

[0045] Please refer to Figure 2 , is a schematic diagram of an example structure of a terminal device provided in an embodiment of the present application. Figure 2 The terminal device shown includes components such as a processor 210, a memory 220, a transceiver 230, a display unit 240, an input unit 250, a sensor 260, an audio circuit 270, and a power module 280.

[0046] The processor 210 is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device. By running or executing software programs and / or modules stored in the memory 220, and calling data stored in the memory 220, the processor 210 performs various functions of the terminal device and processes data, thereby monitoring the terminal device as a whole. Optionally, the processor 210 may include one or more processing units; optionally, the processor 210 may integrate an application processor, which mainly processes operating devices, user interfaces, and application programs, etc. Of course, other processors may also be included, which are not listed here one by one.

[0047] The memory 220 can be used to store software programs and modules. The processor 210 executes various functional applications and data processing of the terminal device by running the software programs and modules stored in the memory 220. The memory 220 can mainly include a program storage area and a data storage area, wherein the program storage area can store operating devices, at least one application required for a function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the terminal device (such as audio data, a phone book, etc.), etc. In addition, the memory 220 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0048] The transceiver 230 can provide wireless communication solutions applied to terminal devices, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc. The transceiver 230 can be one or more devices integrating at least one communication processing module, for example, integrating an antenna and a baseband processor into the transceiver 230, or integrating an antenna and a modem processor into the transceiver 230, etc., which are not limited here.

[0049] The display unit 240 may be used to display information input by the user or information provided to the user and various menus of the terminal device. The display unit 240 may be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc., which is not limited here.

[0050] The input unit 250 can be used to receive input digital or character information, and to generate key signal input related to the user settings and function control of the terminal device. Specifically, the input unit 250 can collect the user's operations on or near it, and drive the corresponding connection device according to a pre-set program. In addition, the input unit 250 may include a touch panel, which can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves. In addition to the touch panel, the input unit 250 may also include other input devices. Specifically, other input devices may include, but are not limited to, one or more of function keys (such as volume control keys, switch keys, etc.), trackballs, joysticks, etc.

[0051] The terminal device may also include at least one sensor 260, such as a gyroscope sensor, a motion sensor, and other sensors. The motion sensor may include an acceleration sensor for detecting the magnitude of acceleration in all directions, and the magnitude and direction of gravity when stationary, which may be used for applications that identify the posture of the terminal device, such as horizontal and vertical screen switching, related games, magnetometer posture calibration, etc. As for other sensors that may be configured in the terminal device, such as a pressure gauge, a barometer, a hygrometer, a thermometer, an infrared sensor, etc., they will not be described in detail here.

[0052] The audio circuit 270 may include a speaker and a microphone, and may provide an audio interface between the user and the terminal device. The audio circuit 270 may transmit the received audio data to the speaker after converting the received audio data into an electrical signal, which is converted into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 270 and converted into audio data, and then the audio data is output to the processor 210 for processing, and then sent to another terminal device through the video circuit, or the audio data is output to the memory 220 for further processing.

[0053] The terminal device also includes a power module 280 for supplying power to various components. Optionally, the power module 280 can be logically connected to the processor 210 through a power management device, so as to manage charging, discharging, power consumption and other functions through the power management device.

[0054] Although not shown, the terminal device may further include a camera. Optionally, the camera may be located at the front or rear of the terminal device, which is not limited in the embodiment of the present application.

[0055] It is to be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the terminal device. In other embodiments of the present application, the terminal device may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0056] Optionally, the above-mentioned terminal devices may include but are not limited to wearable devices (such as smart bracelets, smart watches, smart glasses, etc.), mobile phones, tablet computers, laptops, MP3 players (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Compression Standard Audio Layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Compression Standard Audio Layer 4) players, desktop computers, laptops, etc.

[0057] Usually, the above Figure 2 The normal operation of the terminal device shown needs to be equipped with a corresponding operating system, and various applications are run based on the operating system. For example, the operating system of the terminal device can be an Android system, an iOS system, a Linux system, etc.

[0058] Currently, if the first user wants to add Figure 1 If the character image generated by the terminal device is shared with other users, the complete character image can be sent to other users. When other users want to generate an effect that is exactly the same as the character image, they still need to use their own terminal devices to re-capture the image of the first user and select the same character model, etc., to finally achieve the same effect.

[0059] Therefore, in this application, when the first user shares the dynamic expressions (i.e., character images) generated by him / her, he / she directly sends the generated dynamic expressions to other users. If other users want to generate the same dynamic expressions themselves, they can only download all the data of the dynamic expressions or let the first user use his / her own terminal device to re-collect and generate them. The generation process is cumbersome, the amount of data to be transmitted is large, and there is a problem of low efficiency in generating character images.

[0060] In order to simplify the process of generating a character image and improve the efficiency of generating a character image, the present application provides a character image generation method that can be applied to a first terminal device. By obtaining a model parameter file related to generating a first character image in the first terminal device, the model parameter file can be directly sent to a second terminal device, so that the second terminal device can generate a second character image more quickly.

[0061] Please refer to Figure 3 , which shows a method flow chart of a method for generating a character image provided by an exemplary embodiment of the present application, and the method for generating a character image can be applied to a first terminal device. Figure 3 As shown, the character image generation method may include the following steps:

[0062] Step 301 : obtaining a model parameter file, wherein the model parameter file includes model parameters for adjusting a first character model according to an image collected from a first user to generate a first character image.

[0063] Optionally, the model parameter files may be model parameter files pre-stored in the first terminal device, or the model parameter files may be model parameter files generated in real time by the first terminal device during the process of generating the first character image.

[0064] Optionally, in the first terminal device of the present solution, the first character image is generated based on the image collected from the first user, and the image collected by the user and the first character model selected by the user are used as input parameters of the machine learning model. The machine learning model can adjust the first character model according to the collected image through a preset solution to generate the first character image. The machine learning model is pre-set in the first terminal device.

[0065] Optionally, the model parameter file includes model parameters in the process of adjusting the first character model according to the collected image by the above-mentioned machine learning model to generate the first character image. For example, by adjusting various model parameters, the shape, surface smoothness, eyebrows, eyes, nose, mouth, face, ears, limb position, lines, skin color, etc. of the first character model can be adjusted so that the first character model makes the same expression or action and generates the first character image, so that the generated first character image conforms to the image collected from the first user.

[0066] Optionally, the first character model may be selected by the first user. When the first terminal device captures an image of the first user, after the first user selects the first character model, the first terminal device may autonomously control the front or rear camera to capture the image of the first user.

[0067] Step 302: Send the model parameter file to the second terminal device, so that the second terminal device adjusts the second character model according to the model parameters included in the model parameter file to generate a second character image.

[0068] Optionally, the first terminal device may send the model parameter file to the second terminal device. After receiving the model parameter file, the second terminal device adjusts the second character model according to the model parameters included in the model parameter file to generate the second character image.

[0069] For example, the second user uses the second terminal device, and the first user sends a model parameter file containing model parameters for generating a first character image to the second terminal device through the first terminal device. After receiving the model parameter file, the second terminal device executes a process similar to that of the first terminal device generating the first character image. According to the model parameters contained in the model parameter file, the second character model selected by the second user is adjusted to generate the second character image. The second terminal device does not need to re-capture the image of the first user or download all the data of the first character image. The second terminal device can use the function of generating the second character image itself, which makes it more convenient to share the generated character image between different users.

[0070] In summary, the present application obtains a model parameter file, wherein the model parameter file contains model parameters for adjusting the first character model according to the image collected from the first user to generate the first character image; and sends the model parameter file to the second terminal device, so that the second terminal device adjusts the second character model according to the model parameters contained in the model parameter file to generate the second character image. When sharing the first character image generated by itself, the model parameters for adjusting the first character model according to the image collected from the first user by the first terminal device are packaged into a model parameter file, and the model parameter file is sent to the second terminal device, so that the second terminal device generates the second character image according to the model parameters in the model parameter file. The first terminal device does not need to transmit all the data of the first character image, which reduces the amount of data that needs to be transmitted, so that the second terminal device can generate the second character image more quickly, thereby improving the efficiency of generating the character image.

[0071] The following describes the above-mentioned solution by taking the second terminal device as the execution subject.

[0072] Please refer to Figure 4 , which shows a method flow chart of a method for generating a character image provided by an exemplary embodiment of the present application, and the method for generating a character image can be applied to a second terminal device. Figure 4 As shown, the character image generation method may include the following steps:

[0073] Step 401 , receiving a model parameter file, wherein the model parameter file includes model parameters for a first character image generated by a first terminal device by adjusting a first character model according to an image collected from a first user.

[0074] Optionally, a communication connection is established between the second terminal device and the first terminal device, that is, the first terminal device and the second terminal device can transmit the model parameter file through the communication connection. Optionally, the communication connection can be a wired network connection or a wireless network connection.

[0075] Optionally, the wireless network connection or wired network connection described above uses standard communication technology and / or protocol. The network is usually the Internet, but it can also be any network, including but not limited to any combination of a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a dedicated network or a virtual private network. In some embodiments, the data exchanged through the network is represented by technology and / or format including Hyper Text Mark-up Language (HTML), Extensible Markup Language (XML), etc. In addition, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), Internet Protocol Security (IPsec) can also be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above-mentioned data communication technologies.

[0076] Optionally, the first terminal device and the second terminal device may be installed with the same application. For example, one of the functions of the application is to generate a character model. Different users can send the character images they want to share to other users through the application.

[0077] Step 402: adjusting the second character model according to the model parameters included in the model parameter file to generate a second character image.

[0078] Optionally, after receiving the model parameter file through the second terminal device, the second user selects the second character model in the corresponding application interface, and generates the second character image using the model parameters contained in the model parameter file. Optionally, the second character image generated using the same model parameters as the generated first character image is intuitively the same as the first character image. In other words, a character image that is the same as the first character image can be generated through this generation method.

[0079] In summary, the present application receives a model parameter file, wherein the model parameter file includes model parameters for the first terminal device to adjust the first character model according to the image collected from the first user to generate the first character image; and adjusts the second character model according to the model parameters included in the model parameter file to generate the second character image. When the first terminal device shares the first character image generated by itself with the second terminal device, the model parameters for the first character image generated by the first terminal device by adjusting the first character model according to the image collected from the first user to generate the first character image are packaged into a model parameter file, and the model parameter file is sent to the second terminal device, so that the second terminal device generates the second character image according to the model parameters in the model parameter file, and the first terminal device does not need to transmit all the data of the first character image, which reduces the amount of data that needs to be transmitted, so that the second terminal device can generate the second character image more quickly, and improves the efficiency of generating character images.

[0080] In a possible implementation, the model parameters may further include sub-model parameters for each body part of the first character model, and in the first terminal device, the model parameter file may further include sub-model files divided according to the sub-model parameters for each body part. The user may select different sub-model files, merge the different sub-model files into a new whole, and share it with the second terminal device, thereby increasing the diversity of the shared character images.

[0081] The interaction between the first terminal device and the second terminal device is used to Figure 3 and Figure 4 The embodiments shown are described by way of example. Figure 5 , which shows a method flow chart of a method for generating a character image provided by an exemplary embodiment of the present application, and the method for generating a character image can be applied to a second terminal device. Figure 5 As shown, the character image generation method may include the following steps:

[0082] Step 501: A first terminal device selects a first character model in a character selection interface and captures an image of a first user.

[0083] Optionally, the first user may trigger an application in the first terminal device to enter the character selection interface, or may enter the setting interface through the setting icon of the first terminal device and then trigger a control for generating the first character image provided to the first terminal device to enter the character selection interface.

[0084] Please refer to Figure 6 , which shows a schematic diagram of a character selection interface involved in an exemplary embodiment of the present application. Figure 6 As shown, in the character selection interface 600, various character models to be selected 601 and a first character image 602 are included. Optionally, the first user can select any character model from the character models to be selected 601 as the first character model, that is, in response to the selection operation of the first user, the first terminal device selects the first character model triggered by the first user in the character selection interface. After the first user selects, the first terminal device can turn on the front camera to capture the first user and obtain the image of the first user.

[0085] Step 502: Generate a first character image according to the image and the first character model.

[0086] Optionally, after the first terminal device captures the image, the first character image is generated in real time according to the captured image and the first character model. Optionally, when the first user is satisfied with the generated first character image, the save control 603 can be triggered in the character selection interface 600 to save the generated first character image 602. Optionally, after the first character image is generated, the first character image can be applied, for example, applied to a virtual object displayed by the first terminal device during human-computer interaction, so that the virtual object is displayed with the first character image.

[0087] Optionally, the process of the first terminal device generating the first character image based on the image and the first character model can be completed by a pre-set machine learning model, and the image and the first character model are used as model inputs. The machine learning model can eventually output a first character image and display it in the above-mentioned character selection interface.

[0088] Step 503, recording the model parameters used in generating the first character image, and generating and acquiring a model parameter file.

[0089] Optionally, the first terminal device may record the model parameters used in the process of generating the first character image, package the model parameters, and generate a model parameter file, and the model parameter file may be obtained when it needs to be shared or sent to the second terminal device.

[0090] Optionally, the first character image is a dynamic image, which may be a dynamic expression image or an action posture image, and the first character image is dynamic. The first terminal device records the model parameters used in generating the first character image, and generates and obtains the model parameter file, which may be as follows: recording the model parameters used when adjusting the first character model according to each frame of the image during the generation of the first character image; and generating and obtaining the model parameter file corresponding to the first character image according to the recorded model parameters of each frame corresponding to the first character image.

[0091] Since the first character image is a dynamic image, the image collected by the first terminal device is also dynamic, that is, the first terminal device can form a dynamic image based on each frame of the image, and generate the first character image based on the dynamic image and the first character model. Optionally, when the first character image is generated based on the machine learning model, the machine learning model also adjusts the first character model according to each frame of the image, so as to obtain the image of the first character image corresponding to each frame of the image, and the first character image finally output is also the character image of each frame, so as to obtain a dynamic image. In this process, the first terminal device records the model parameters used when adjusting the first character model according to each frame of the image in the process of generating the first character image, packages the model parameters of each frame, thereby generating a model parameter file corresponding to the first character image, and obtains the generated model parameter file.

[0092] Optionally, the first terminal device can directly obtain the model parameter file corresponding to the first character image during the process of generating the first character image, and perform subsequent sharing and sending processes. Of course, the first terminal device can also store the generated model parameter file in its own memory, and obtain the model parameter file selected by the first user when the first user wants to share it at any time. This application is not limited to this.

[0093] Taking the above-mentioned first user as an example, who can independently select the model parameter file he wants to share, a file selection interface can be displayed in the first terminal device, which includes the model parameter files and selection controls corresponding to the different first characters generated by the first terminal device; in response to the selection operation of any selection control in the file selection interface, the model parameter files corresponding to the selection operation are obtained.

[0094] Please refer to Figure 7 , which shows a schematic diagram of a file selection interface involved in an exemplary embodiment of the present application. Figure 7As shown, in the file selection interface 700, various model parameter files 701 to be selected and various selection controls 702 are included. Among them, each model parameter file 701 is recorded and generated when the first terminal device previously generates a first character image. When the user wants to send a model parameter file of a first character image to other users, the user can enter the file selection interface and trigger any one or more selection controls 702 therein, thereby selecting the model parameter file, so that the first terminal device obtains various model parameter files corresponding to the selection operation.

[0095] Optionally, in the present application, the model parameters include various sub-model parameters for various body parts of the first character model, the model parameter file includes various sub-model files divided according to the various sub-model parameters of various body parts, and the above-mentioned file selection interface also includes a merge control, and obtaining the model parameter file includes: responding to the selection operation of at least two selection controls in the file selection interface, and triggering the merge control, merging at least two model parameter files and / or sub-model files corresponding to the selection operation; and obtaining the new model parameter file generated after the merging.

[0096] For example, for the first character model mentioned above, the first character model is a three-dimensional head model of the head. In the process of the machine learning model generating the first character image for the three-dimensional head model, it is divided according to each body part, such as eyes, nose, cheeks, eyebrows, mouth and other parts. Then, when generating the above model parameter file, the first terminal device will divide different model parameters according to these divided body parts, and generate various sub-model files. Each sub-model file includes the model parameters used when adjusting a part of the first character model. If the first character model is divided into 5 parts, then there are also 5 sub-model files generated, and the first terminal device packages these 5 sub-model files into one model parameter file.

[0097] Please refer to Figure 8 , which shows a schematic diagram of another file selection interface involved in an exemplary embodiment of the present application. Figure 8 As shown, in the file selection interface 800, each model parameter file 801 to be selected, a sub-model file 802, each selection control 803, and a merge control 804 are included. Each model parameter file 801 and sub-model file are recorded and generated when the first terminal device generates a first character image before. Figure 8In the embodiment, the first user can select two sub-model files under the model parameter file and another two sub-model files under the model parameter file 2 through the selection controls 803, and trigger the merge control 804. The first terminal device will merge at least two model parameter files and / or sub-model files corresponding to the selection operation; obtain the new model parameter file generated after the merger, realize the combination of different character images, such as combining the nose of the first character image and the mouth of the second character image to form a new character image, etc., to improve the richness of the shared character images.

[0098] It should be noted that the above merging process can be executed in the first terminal device or in the second terminal device. When executed in the second terminal device, the first terminal device can directly send each model parameter file or sub-model file selected by the first user to the second terminal device, and the second terminal device merges these files after receiving them, which is not limited here.

[0099] Optionally, after generating a new model parameter file, the first terminal device can also preview according to the new model parameter file and display the synthesized character image in the preview interface. After the first user confirms that the character image is the one he wants to share, he triggers the sharing or sending control to send the model parameter file to the second terminal device.

[0100] Optionally, when the above-mentioned dynamic image is a dynamic expression image, the model parameters used in the machine learning model may include an expression coefficient and a head posture coefficient. In the above-mentioned process of generating the first character image, the first character model is adjusted by the expression coefficient and the head posture coefficient to generate a first character image that conforms to the image of the first user.

[0101] Optionally, when the above-mentioned dynamic image is an action posture image, the model parameters used in the machine learning model may include human posture coefficients. In the above-mentioned process of generating the first character image, the first character model is adjusted by the human posture coefficients to generate a first character image that conforms to the image of the first user.

[0102] Step 504: Send the model parameter file to the second terminal device.

[0103] Optionally, the first user can perform corresponding operations in the first terminal device to send the model parameters of the first character image to be shared to the second terminal device, so that after the second terminal device obtains the model parameter file, the second terminal device adjusts the second character model according to the model parameters contained in the model parameter file to generate a second character image.

[0104] For example, the file selection interface may also include a sending control. After the first user selects the model parameter file or sub-parameter file that he wants to share in the file selection interface, the first terminal device sends the model parameter file selected by the first user to the second terminal device. Alternatively, after the first character image is generated through the character selection interface, the first terminal device directly obtains the corresponding model parameter file. The first user can trigger the sending or sharing control, and the first terminal device sends the model parameter file obtained in the process of generating the first character image to the second terminal device.

[0105] Step 505: Receive a model parameter file.

[0106] The model parameter file includes model parameters of the first character image generated by the first terminal device adjusting the first character model according to the image collected from the first user. The second terminal device can receive the model parameter file sent by the first terminal device through the communication connection.

[0107] Please refer to Fig. 9 , which shows a schematic diagram of an interface of a file receiving interface involved in an exemplary embodiment of the present application. Fig. 9 As shown, the file receiving interface 900 includes the received model parameter files 901. Optionally, the user can trigger the model parameter file 901 in the second terminal device so that the second terminal device downloads the model parameter file.

[0108] Optionally, in the above description, when the first character image is a dynamic image, the model parameter file is generated by the first terminal device according to the model parameters of each frame corresponding to the recorded first character image, and the model parameters may include various sub-model parameters for various body parts of the first character model, and the model parameter file includes various sub-model files divided according to the various sub-model parameters of various body parts. In this case, after receiving the model parameter file, a file editing interface can also be displayed in the second terminal device, and the file editing interface is used to edit and modify the content of the model parameter file; in response to the editing and modification operation performed on the model parameter file, the edited and modified model parameter file is obtained.

[0109] Please refer to Fig.10 , which shows a schematic diagram of a file editing interface involved in an exemplary embodiment of the present application. Fig.10As shown, in the file editing interface 1000, each model parameter file to be selected 1001, a sub-model file 1002, a file editing box 1003, each selection control 1004, a confirmation control 1005, and a cancel control 1006 are included. When the second user selects any one of the model parameter files or sub-model files through the selection control 1004, each model parameter can be displayed in the file editing box 1003. The second user can edit and modify each model parameter in the file editing box 1003 and trigger the confirmation control 1005, so that the second terminal device can obtain the edited model parameter file. Optionally, there are many ways to enter the file editing interface, such as Fig. 9 Long press any model parameter file in the file receiving interface shown to enter the file editing interface, which is not limited in this solution.

[0110] Taking the first character image as an example, after dividing into various body parts, the model parameters contained in the first sub-model file include parameter one and parameter two, and the model parameters contained in the second sub-model file include parameter three and parameter four. However, after the first terminal device sends the first sub-model file and the second sub-model file to the second terminal device, the model parameter file that the second terminal device can receive includes the first sub-model file and the second sub-model file. When the second sub-model file is selected in the file editing interface, the specific values ​​of parameter three and parameter four will be displayed in the file editing box, and the second user can edit and modify the specific values ​​of parameter three and parameter four in the file editing box.

[0111] Optionally, when merging different sub-model files or model parameter files mentioned in the above step 503, it can also be performed by the second terminal device in this step. That is, the second terminal device can also display a file selection interface, which includes various model parameter files, various sub-model files, various selection controls and merge controls; each selection control is used to select each model parameter file and / or sub-model file. In response to the selection operation of at least two selection controls in the file selection interface, and triggering the merge control, at least two model parameter files and / or sub-model files corresponding to the selection operation are merged. For example, after receiving the model parameter file, the user of the second terminal device clicks on the model parameter file to enter the above file selection interface, and selects the various sub-model files or model parameter files to be merged in the file selection interface. The merging process can refer to the description in step 503, which will not be repeated here.

[0112] Step 506: Select a second character model in the character selection interface.

[0113] Optionally, the second terminal device may also display a display similar to the above Figure 6The character selection interface shown in the figure selects the second character model in the character selection interface. The process of the second terminal device selecting the second character model is similar to the process of the first terminal device selecting the first character model, which will not be repeated here.

[0114] In a possible implementation, the model parameter file has its own corresponding file type, and the second terminal device can determine the file type of the model parameter file; display the character selection interface according to the file type of the model parameter file, and the character selection interface includes various character models to be selected that conform to the file type. For example, the first character image mentioned above is a dynamic expression image or an action posture image, and when the first terminal device generates the model parameter file, it will be named as an expression file or an action file, that is, if the generated first character image is a dynamic expression image, the model parameter file is named as an expression file, and if the generated first character image is an action posture image, then the model parameter file is named as an action file.

[0115] Optionally, the second terminal device may obtain the name of the model parameter file, determine whether the file type of the model parameter file is an expression type or an action type according to the name of the model parameter file, and display each character model that conforms to the file type when displaying the character selection interface. If the file type of the model parameter file is an expression type, then each character model is a three-dimensional head model of the character, and if the file type of the model parameter file is an action type, then each character model is a three-dimensional limb model of the character.

[0116] Optionally, if in the above merging scheme, a model parameter file of an expression class and a model parameter file of an action class are merged, they can be named a mixed file. The name of the mixed file can indicate that the model parameter file contains both the model parameter file of the expression class of the three-dimensional head model and the model parameter file of the action class of the three-dimensional limb model. In the character selection interface, a character model combining the three-dimensional head module and the three-dimensional limb model is displayed.

[0117] Step 507: In response to the selection operation on the model parameter file, the model parameters included in the model parameter file are obtained.

[0118] Optionally, in the second terminal device, the model parameter file may be selected in the above-mentioned file selection interface, or the model parameter file may be selected in the character selection interface.

[0119] Normally, the second terminal device and the first terminal device automatically start the front camera to shoot after displaying the character selection interface, but the user can also trigger the target control in the character selection interface and select the "select file control". Accordingly, the second terminal device can enter the above-mentioned file selection interface, and then provide the user with the option to select the model parameter file he wants to use.

[0120] For example, please refer to Fig.11 , which shows an interface schematic diagram of another character selection interface involved in an exemplary embodiment of the present application. Fig.11 As shown, in the character selection interface 1100, various character models to be selected 1101, a second character image 1102, a target control 1103, and a select file control 1104 are included. Optionally, in the character selection interface 1100 displayed by the second terminal device, the user can select any character model from the character models to be selected 1101 as the second character model, and the user can also trigger the target control 1103 to display the select file control 1104, enter the above file selection interface, and then select the model parameter file to be used.

[0121] Step 508: Adjust the second character model according to the model parameters to generate a second character image.

[0122] Optionally, the second terminal device adjusts the second character model according to the model parameters in the selected model parameter file to generate a second character image. Among them, the implementation method of the second terminal device generating the second character image can be similar to the method of the first terminal device generating the first character image, which will not be repeated here. For example, after selecting the model parameter file in the second terminal device, the application control is triggered to apply the selected model parameter file to the second character model, so that the second terminal device adjusts the second character model according to the model parameters in the selected model parameter file to generate a second character image. In other words, this solution can apply the model parameter file of the first character image to the second character model with one click to generate a second character image that is the same as the first character image.

[0123] Optionally, the second character model may not need to be selected by the user, and the model parameter file may carry the number or identifier of the specific first character model. The second terminal device may obtain the number or identifier of the first character model in the model parameter file, and select the character model with the same number or identifier as the second character model in the second terminal device, and then adjust the second character model with the model parameters to generate a second character image.

[0124] Optionally, the above-mentioned determination of the file type of the model parameter file may also be applied in this step. After determining the file type of the model parameter file, a second character model having the same file type as the model parameter file is driven to generate a second character image.

[0125] It should be noted that the first character image and the second character image mentioned above are exemplified by the human body. In actual application, they may also be images of other animals, which will not be elaborated here.

[0126] In summary, the present application obtains a model parameter file, wherein the model parameter file contains model parameters for adjusting the first character model according to the image collected from the first user to generate the first character image; and sends the model parameter file to the second terminal device, so that the second terminal device adjusts the second character model according to the model parameters contained in the model parameter file to generate the second character image. When sharing the first character image generated by itself, the model parameters for adjusting the first character model according to the image collected from the first user by the first terminal device are packaged into a model parameter file, and the model parameter file is sent to the second terminal device, so that the second terminal device generates the second character image according to the model parameters in the model parameter file. The first terminal device does not need to transmit all the data of the first character image, which reduces the amount of data that needs to be transmitted, so that the second terminal device can generate the second character image more quickly, thereby improving the efficiency of generating the character image.

[0127] In addition, the present application can also record each sub-model parameter for each body part of the first character model, and generate each sub-model file, and flexibly merge each sub-model file or model parameter file to improve the diversity of the generated first character image. In addition, the user can also perform secondary editing on the received model parameter file, and share the secondary edited model parameter file, for example, the expression and action can be merged into one file, so that the face and body can be driven simultaneously when used on the character model.

[0128] Next, taking a mobile phone as an example, two dynamic images can be generated in the mobile phone, namely a dynamic expression image and an action posture image. The action expression image is generated by adjusting the virtual three-dimensional head model, and the action posture image is generated by adjusting the virtual three-dimensional body model.

[0129] Please refer to Fig.12 , which shows a method flow chart of a method for generating a character image provided by an exemplary embodiment of the present application, and the method for generating a character image can be applied to a first mobile phone and a second mobile phone. Fig.12 As shown, the character image generation method may include the following steps:

[0130] Step 1201: The first mobile phone turns on the camera to capture an image of the first user.

[0131] Step 1202: The first mobile phone generates a dynamic expression image.

[0132] Step 1203, recording the expression coefficient and head posture coefficient of each frame.

[0133] Step 1204, package and name it as an expression file.

[0134] Step 1205: the first mobile phone generates an action posture image.

[0135] Step 1206, recording the human body posture coefficient of each frame.

[0136] Step 1207, package and name it as an action file.

[0137] Optionally, steps 1202 to 1204, and steps 1205 to 1207 can be selected by the first user. The first user selects a model in the character selection interface, and the corresponding steps are executed. For example, if the model for generating a dynamic expression image is selected, steps 1202 to 1204 are executed. If the model for generating an action posture image is selected, steps 1205 to 1207 are executed. The expression file or action file here is equivalent to the model parameter file in the above embodiment.

[0138] Step 1208, save locally and send to the second mobile phone.

[0139] Step 1209: The second mobile phone receives the expression file or the action file and applies it.

[0140] Optionally, after receiving the model parameter file, the second mobile phone applies it to its own model to facilitate subsequent generation of the same dynamic image.

[0141] Step 1210, determine the file type.

[0142] Step 1211, driving the expression character model to generate the same dynamic expression image.

[0143] Step 1212, driving the action-type character model to generate the same action posture image.

[0144] Optionally, when the second mobile phone drives the generation of the dynamic image, it determines which character model to drive according to the file type, and if it is an expression type, it drives the character model of the expression type to generate the same dynamic expression image. If it is an action type, it drives the character model of the action type to generate the same action posture image.

[0145] In summary, after recording a dynamic expression image or action posture image locally on the first mobile phone, if you want the second mobile phone to generate the same dynamic expression image or action posture image, the first mobile phone only needs to send the expression file and action file to the second mobile phone, and the second mobile phone will apply the received expression file and action file to its own character model, which enriches the diversity of the character model generation process and increases the fun of the dynamic image. In addition, users can make their favorite dynamic expression images or action posture images and share them with friends, which increases the fun of using dynamic images and the spread rate of actions, no longer relying on designers to design model actions, and reduces communication costs and design costs.

[0146] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0147] Please refer to Fig.13 , which shows a structural block diagram of a character image generation device provided by an exemplary embodiment of the present application. The character image generation device 1300 can be used in a first terminal device. Figure 3 , Figure 5 or Fig.12 All or part of the steps in the method provided by the illustrated embodiment are performed by the first terminal device. The character image generation device 1300 includes:

[0148] A first acquisition module 1301 is used to acquire a model parameter file, wherein the model parameter file includes model parameters for generating a first character image by adjusting a first character model according to an image collected from a first user;

[0149] The first sending module 1302 is used to send the model parameter file to the second terminal device, so that the second terminal device adjusts the second character model according to the model parameters included in the model parameter file to generate a second character image.

[0150] In summary, the present application obtains a model parameter file, wherein the model parameter file contains model parameters for adjusting the first character model according to the image collected from the first user to generate the first character image; and sends the model parameter file to the second terminal device, so that the second terminal device adjusts the second character model according to the model parameters contained in the model parameter file to generate the second character image. When sharing the first character image generated by itself, the model parameters for adjusting the first character model according to the image collected from the first user by the first terminal device are packaged into a model parameter file, and the model parameter file is sent to the second terminal device, so that the second terminal device generates the second character image according to the model parameters in the model parameter file. The first terminal device does not need to transmit all the data of the first character image, which reduces the amount of data that needs to be transmitted, so that the second terminal device can generate the second character image more quickly, thereby improving the efficiency of generating the character image.

[0151] Optionally, the first acquisition module 1301 includes: a first selection unit, a first generation unit and a first acquisition unit;

[0152] The first selection unit is used to select a first character model in the character selection interface and collect an image of the first user;

[0153] The first generating unit is used to generate a first character image according to the image and the first character model;

[0154] The first acquisition unit is used to record the model parameters used in generating the first character image, and to generate and acquire the model parameter file.

[0155] Optionally, the first character image is a dynamic image, and the first acquisition unit includes: a first recording subunit and a first acquisition subunit;

[0156] The first recording subunit is used to record the model parameters used when adjusting the first character model according to each frame of image during the process of generating the first character image;

[0157] The first acquisition subunit is used to generate and acquire the model parameter file corresponding to the first character image according to the recorded model parameters of each frame corresponding to the first character image.

[0158] Optionally, the first acquisition module 1301 includes: a first display unit and a second acquisition unit;

[0159] The first display unit is used to display a file selection interface, wherein the file selection interface includes various model parameter files and various selection controls corresponding to different first character images generated by the first terminal device;

[0160] The second acquisition unit is used to respond to a selection operation on any selection control in the file selection interface and acquire each model parameter file corresponding to the selection operation.

[0161] Optionally, the model parameters include various sub-model parameters for various body parts of the first character model, the model parameter file includes various sub-model files divided according to the various sub-model parameters of the various body parts, the file selection interface also includes a merging control, and the first acquisition module 1301 includes: a first merging unit, a third acquisition unit;

[0162] The first merging unit is used to respond to a selection operation on at least two selection controls in the file selection interface and trigger the merging control to merge the at least two model parameter files and / or sub-model files corresponding to the selection operation;

[0163] The third acquisition unit is used to acquire the new model parameter file generated after the merging.

[0164] Optionally, the dynamic image is a dynamic expression image, and the model parameters include an expression coefficient and a head posture coefficient; or,

[0165] The dynamic image is an action posture image, and the model parameters include human body posture coefficients.

[0166] Please refer to Fig.14 , which shows a structural block diagram of a character image generation device provided by an exemplary embodiment of the present application. The character image generation device 1400 can be used in a second terminal device. Figure 4 , Figure 5 or Fig.12 All or part of the steps in the method provided by the illustrated embodiment are performed by the second terminal device. The character image generation device 1400 includes:

[0167] A first receiving module 1401 is used to receive a model parameter file, wherein the model parameter file includes model parameters of a first character image generated by adjusting a first character model by a first terminal device according to an image collected from a first user;

[0168] The first generating module 1402 is used to adjust the second character model according to the model parameters included in the model parameter file to generate a second character image.

[0169] In summary, the present application receives a model parameter file, wherein the model parameter file includes model parameters for the first terminal device to adjust the first character model according to the image collected from the first user to generate the first character image; and adjusts the second character model according to the model parameters included in the model parameter file to generate the second character image. When the first terminal device shares the first character image generated by itself with the second terminal device, the model parameters for the first character image generated by the first terminal device by adjusting the first character model according to the image collected from the first user to generate the first character image are packaged into a model parameter file, and the model parameter file is sent to the second terminal device, so that the second terminal device generates the second character image according to the model parameters in the model parameter file, and the first terminal device does not need to transmit all the data of the first character image, which reduces the amount of data that needs to be transmitted, so that the second terminal device can generate the second character image more quickly, and improves the efficiency of generating character images.

[0170] Optionally, the first generating module 1402 includes: a second selecting unit, a fourth acquiring unit, and a second generating unit;

[0171] The second selection unit is used to select a second character model in the character selection interface;

[0172] The fourth acquisition unit is used for acquiring the model parameters contained in the model parameter file in response to a selection operation on the model parameter file;

[0173] The second generating unit is used to adjust the second character model according to the model parameters to generate the second character image.

[0174] Optionally, both the second character image and the first character image are dynamic images, and the model parameter file is generated by the first terminal device according to the recorded model parameters of each frame corresponding to the first character image.

[0175] Optionally, the model parameters include various sub-model parameters for various body parts of the first character model, and the model parameter file includes various sub-model files divided according to the various sub-model parameters for the various body parts.

[0176] Optionally, the device further comprises:

[0177] The first display module is used to display a file selection interface, which includes various model parameter files, various sub-model files, various selection controls and a merge control; each selection control is used to select each model parameter file and / or sub-model file.

[0178] The first merging module is used to respond to the selection operation of at least two selection controls in the file selection interface and trigger the merging control to merge the at least two model parameter files and / or sub-model files corresponding to the selection operation.

[0179] Optionally, the device further comprises:

[0180] A first determination module, used for determining the file type of the model parameter file before adjusting the second character model to generate the second character image according to the model parameters included in the model parameter file;

[0181] The second display module is used to display a character selection interface according to the file type of the model parameter file, and the character selection interface contains various character models to be selected that conform to the file type.

[0182] Optionally, the device further comprises:

[0183] A third display module is used to display a file editing interface after receiving the model parameter file, and the file editing interface is used to edit and modify the content of the model parameter file;

[0184] The second acquisition module is used to acquire the edited model parameter file in response to the edit and modification operation performed on the model parameter file.

[0185] Please refer to Fig.15 , which is a structural diagram of another example of the character image generation device provided in the embodiment of the present application. Among them, the character image generation device 1500 can be a first terminal device or a second terminal device, which can realize the functions in the method provided in the embodiment of the present application. Among them, the character image generation device 1500 can be a chip system. In the embodiment of the present application, the chip system can be composed of a chip, or it can include a chip and other discrete devices.

[0186] In hardware implementation, the above-mentioned communication module can be a transceiver, and the transceiver is integrated in the character image generation device 1500 to form a communication interface 1503.

[0187] The character image generation device 1500 includes at least one processor 1501, which is used to implement or support the character image generation device 1500 to implement the functions of the terminal device in the method provided in the embodiment of the present application. Exemplarily, the processor 1501 can execute the steps of obtaining a model parameter file, which includes the model parameters for adjusting the first character model according to the image collected from the first user to generate the first character image; sending the model parameter file to the second terminal device, so that the second terminal device adjusts the second character model according to the model parameters included in the model parameter file to generate the second character image. Alternatively, the steps of receiving a model parameter file, which includes the model parameters for adjusting the first character model according to the image collected from the first user by the first terminal device to generate the first character image; adjusting the second character model according to the model parameters included in the model parameter file to generate the second character image. Please refer to the detailed description in the method example for details, which will not be repeated here.

[0188] The character image generation device 1500 may also include at least one memory 1502 for storing program instructions and / or data. The memory 1502 is coupled to the processor 1501. The coupling in the embodiment of the present application is an indirect coupling or communication connection between devices, units or modules, which may be electrical, mechanical or other forms, and is used for information exchange between devices, units or modules. The processor 1501 may operate in conjunction with the memory 1502. The processor 1501 may execute program instructions stored in the memory 1502. At least one of the at least one memory may be included in the processor.

[0189] The character image generation device 1500 may also include a communication interface 1503, which is used to communicate with other devices through a transmission medium, so that the device in the character image generation device 1500 can communicate with other devices. Exemplarily, the other device may be a network side device. The processor 1501 may use the communication interface 1503 to send and receive data. The communication interface 1503 may specifically be a transceiver.

[0190] The specific connection medium between the communication interface 1503, the processor 1501 and the memory 1502 is not limited in the embodiment of the present application. Fig.15 In the embodiment, the memory 1502, the processor 1501 and the communication interface 1503 are connected via a bus 1504. Fig.15 The connections between the other components are shown in bold lines, which are only for illustration and are not intended to be limiting. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.15 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0191] In the embodiment of the present application, the processor 1501 can be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and can implement or execute the methods, steps and logic block diagrams disclosed in the embodiment of the present application. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware processor to be executed, or can be executed by a combination of hardware and software modules in the processor.

[0192] In the embodiment of the present application, the memory 1502 can be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), etc., and can also be a volatile memory (volatile memory), such as a random access memory (RAM). The memory is any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this. The memory in the embodiment of the present application can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0193] Optionally, an embodiment of the present application also provides a terminal device, the terminal device includes a processor and a memory, the memory stores a computer program, and the computer program is executed by the processor to implement all or part of the steps performed by the first terminal device or the second terminal device in the character image generation method described in the above embodiments.

[0194] Optionally, an embodiment of the present application further provides a computer-readable medium storing a computer program, which is executed by a processor to implement all or part of the steps performed by the first terminal device or the second terminal device in the character image generation method described in the above embodiments.

[0195] Optionally, an embodiment of the present application also provides a computer program product, which stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set are loaded and executed by the processor to implement the character image generation method described in the above embodiments, all or part of the steps executed by the first terminal device or the second terminal device.

[0196] It should be noted that: when the device provided in the above embodiment performs the control of the electronic device, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0197] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0198] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0199] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for generating a character image, characterized in that: Applied to a first terminal device, the method includes: Acquire a model parameter file, wherein the model parameter file includes model parameters for adjusting a first character model according to an image collected from a first user to generate a first character image; The model parameter file is sent to a second terminal device, so that the second terminal device adjusts the second character model according to the model parameters included in the model parameter file to generate a second character image.

2. The method according to claim 1, characterized in that The obtaining of the model parameter file comprises: Selecting a first character model in a character selection interface, and capturing an image of the first user; generating a first character image according to the image and the first character model; The model parameters used in generating the first character image are recorded, and the model parameter file is generated and obtained.

3. The method according to claim 2, characterized in that The first character image is a dynamic image, and the model parameters used in generating the first character image are recorded, and the model parameter file is generated and obtained, including: Recording the model parameters used when adjusting the first character model according to each frame of image during the process of generating the first character image; The model parameter file corresponding to the first character image is generated and obtained according to the recorded model parameters of each frame corresponding to the first character image.

4. The method according to claim 1, characterized in that: The obtaining of the model parameter file comprises: Displaying a file selection interface, wherein the file selection interface includes model parameter files and selection controls corresponding to different first character images generated by the first terminal device; In response to a selection operation on any selection control in the file selection interface, each model parameter file corresponding to the selection operation is obtained.

5. The method according to claim 4, characterized in that The model parameters include each sub-model parameter for each body part of the first character model, the model parameter file includes each sub-model file divided according to each sub-model parameter of each body part, the file selection interface also includes a merge control, and the obtaining of the model parameter file includes: In response to a selection operation on at least two selection controls in the file selection interface, the merging control is triggered to merge the at least two model parameter files and / or sub-model files corresponding to the selection operation; Get the new model parameter file generated after merging.

6. The method according to any one of claims 1 to 5, characterized in that: The dynamic image is a dynamic expression image, and the model parameters include expression coefficients and head posture coefficients; or, The dynamic image is an action posture image, and the model parameters include human body posture coefficients.

7. A method for generating a character image, characterized in that: Applied to a second terminal device, the method includes: Receiving a model parameter file, wherein the model parameter file includes model parameters for the first terminal device to adjust the first character model according to the image collected from the first user to generate the first character image; According to the model parameters included in the model parameter file, the second character model is adjusted to generate a second character image.

8. The method according to claim 7, characterized in that Adjusting the second character model to generate a second character image according to the model parameters included in the model parameter file includes: Select the second character model in the character selection interface; In response to a selection operation on the model parameter file, acquiring the model parameters contained in the model parameter file; The second character model is adjusted according to the model parameters to generate the second character image.

9. The method according to claim 7, characterized in that: The second character image and the first character image are both dynamic images, and the model parameter file is generated by the first terminal device according to the recorded model parameters of each frame corresponding to the first character image.

10. The method according to claim 9, characterized in that The model parameters include various sub-model parameters for various body parts of the first character model, and the model parameter file includes various sub-model files divided according to the various sub-model parameters for the various body parts.

11. The method according to claim 10, characterized in that The method further comprises: Displaying a file selection interface, wherein the file selection interface includes various model parameter files, various sub-model files, various selection controls, and a merge control; each selection control is used to select various model parameter files and / or sub-model files; In response to a selection operation on at least two selection controls in the file selection interface, the merging control is triggered, and the at least two model parameter files and / or sub-model files corresponding to the selection operation are merged.

12. The method according to any one of claims 7 to 11, characterized in that: Before adjusting the second character model to generate the second character image according to the model parameters included in the model parameter file, the method further includes: Determine the file type of the model parameter file; A character selection interface is displayed according to the file type of the model parameter file, and the character selection interface includes various character models to be selected that conform to the file type.

13. The method according to any one of claims 7 to 11, characterized in that: After receiving the model parameter file, the method further includes: Displaying a file editing interface, wherein the file editing interface is used to edit and modify the content of the model parameter file; In response to the editing and modifying operation performed on the model parameter file, the edited and modified model parameter file is obtained.

14. A character image generation device, characterized in that: Applied to a first terminal device, the apparatus comprises: A first acquisition module, used to acquire a model parameter file, wherein the model parameter file includes model parameters for generating a first character image by adjusting a first character model according to an image collected from a first user; The first sending module is used to send the model parameter file to the second terminal device, so that the second terminal device adjusts the second character model according to the model parameters included in the model parameter file to generate a second character image.

15. A character image generation device, characterized in that: Applied to a second terminal device, the apparatus comprises: A first receiving module, configured to receive a model parameter file, wherein the model parameter file includes model parameters of a first character image generated by adjusting a first character model by a first terminal device according to an image collected from a first user; The first generating module is used to adjust the second character model according to the model parameters included in the model parameter file to generate a second character image.

16. A terminal device, characterized in that: The terminal device includes a processor and a memory, wherein a computer program is stored in the memory, and the computer program is executed by the processor to implement the character image generation method as described in any one of claims 1 to 6 or 7 to 13.

17. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is executed by a processor to implement the method for generating a human image as described in any one of claims 1 to 6 or 7 to 13.

Images